# Harnessing Unrecognizable Faces for Improving Face Recognition

arXiv: https://arxiv.org/abs/2106.04112 · HTML: https://mlsanity.com/paper/2106.04112/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Data Uncertainty Learning in Face Recognition](https://mlsanity.com/paper/2003.11339/) (2020)
- [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [Towards causal benchmarking of bias in face analysis algorithms](https://mlsanity.com/paper/2007.06570/) (2020)
- [FaceQnet: Quality Assessment for Face Recognition based on Deep Learning](https://mlsanity.com/paper/1904.01740/) (2019)
- [Feature Space Singularity for Out-of-Distribution Detection](https://mlsanity.com/paper/2011.14654/) (2020)
- [Neural Aggregation Network for Video Face Recognition](https://mlsanity.com/paper/1603.05474/) (2016)
- [Biometric Quality: Review and Application to Face Recognition with FaceQnet](https://mlsanity.com/paper/2006.03298/) (2020)
- [Unsupervised Domain-Specific Deblurring via Disentangled Representations](https://mlsanity.com/paper/1903.01594/) (2019)
- [Studying Very Low Resolution Recognition Using Deep Networks](https://mlsanity.com/paper/1601.04153/) (2016)
- [Quality Aware Network for Set to Set Recognition](https://mlsanity.com/paper/1704.03373/) (2017)
- [Template Adaptation for Face Verification and Identification](https://mlsanity.com/paper/1603.03958/) (2016)
- [Multicolumn Networks for Face Recognition](https://mlsanity.com/paper/1807.09192/) (2018)
- [Comparator Networks](https://mlsanity.com/paper/1807.11440/) (2018)
- [Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)](https://mlsanity.com/paper/1902.07327/) (2019)
- [Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets](https://mlsanity.com/paper/1907.03030/) (2019)
- [Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition](https://mlsanity.com/paper/1908.01174/) (2019)

## Built on by (most cited first, 7 of 7)

- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [STC speaker recognition systems for the NIST SRE 2021](https://mlsanity.com/paper/2111.02298/) (2021)
- [Holistic Uncertainty Estimation For Open-Set Recognition](https://mlsanity.com/paper/2408.14229/) (2024)
- [CCFace: Classification Consistency for Low-Resolution Face Recognition](https://mlsanity.com/paper/2308.09230/) (2023)
- [IG-FIQA: Improving Face Image Quality Assessment through Intra-class Variance Guidance robust to Inaccurate Pseudo-Labels](https://mlsanity.com/paper/2403.08256/) (2024)
- [Boosting Unconstrained Face Recognition with Targeted Style Adversary](https://mlsanity.com/paper/2408.07642/) (2024)
- [Quality-Aware Prototype Memory for Face Representation Learning](https://mlsanity.com/paper/2311.07734/) (2023)

## Abstract (arXiv)

The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector. When the detector succeeds, it can detect faces that cannot be recognized, no matter how capable the recognition system. Recognizability, a latent variable, should therefore be factored into the design and implementation of face recognition systems. We propose a measure of recognizability of a face image that leverages a key empirical observation: an embedding of face images, implemented by a deep neural network trained using mostly recognizable identities, induces a partition of the hypersphere whereby unrecognizable identities cluster together. This occurs regardless of the phenomenon that causes a face to be unrecognizable, it be optical or motion blur, partial occlusion, spatial quantization, poor illumination. Therefore, we use the distance from such an "unrecognizable identity" as a measure of recognizability, and incorporate it in the design of the over-all system. We show that accounting for recognizability reduces error rate of single-image face recognition by 58% at FAR=1e-5 on the IJB-C Covariate Verification benchmark, and reduces verification error rate by 24% at FAR=1e-5 in set-based recognition on the IJB-C benchmark.